END-TO-END LEARNING OF PROBABILISTIC HIERARCHIES ON GRAPHS

Daniel Zügner; Bertrand Charpentier; Sascha Geringer; Morgane Ayle; Stephan Günnemann

END-TO-END LEARNING OF PROBABILISTIC HIERARCHIES ON GRAPHS

Daniel Zügner, Bertrand Charpentier, Sascha Geringer, Morgane Ayle, Stephan Günnemann

Informatics 26 - Chair of Professorship of Data Analytics and Machine Learning

Technical University of Munich

Research output: Contribution to conference › Paper › peer-review

Abstract

We propose a novel probabilistic model over hierarchies on graphs obtained by continuous relaxation of tree-based hierarchies. We draw connections to Markov chain theory, enabling us to perform hierarchical clustering by efficient end-to-end optimization of relaxed versions of quality metrics such as Dasgupta cost or Tree-Sampling Divergence (TSD). We show that our model learns rich, high-quality hierarchies present in 11 real world graphs, including a large graph with 2.3M nodes. Our model consistently outperforms recent as well as strong traditional baselines such as average linkage. Our model also obtains strong results on link prediction despite not being trained on this task, highlighting the quality of the hierarchies discovered by our model.

Original language	English
State	Published - 2022
Event	10th International Conference on Learning Representations, ICLR 2022 - Virtual, Online Duration: 25 Apr 2022 → 29 Apr 2022

Conference

Conference	10th International Conference on Learning Representations, ICLR 2022
City	Virtual, Online
Period	25/04/22 → 29/04/22

Cite this

@conference{82b3116e1e16416c8f5fc324b407de96,

title = "END-TO-END LEARNING OF PROBABILISTIC HIERARCHIES ON GRAPHS",

abstract = "We propose a novel probabilistic model over hierarchies on graphs obtained by continuous relaxation of tree-based hierarchies. We draw connections to Markov chain theory, enabling us to perform hierarchical clustering by efficient end-to-end optimization of relaxed versions of quality metrics such as Dasgupta cost or Tree-Sampling Divergence (TSD). We show that our model learns rich, high-quality hierarchies present in 11 real world graphs, including a large graph with 2.3M nodes. Our model consistently outperforms recent as well as strong traditional baselines such as average linkage. Our model also obtains strong results on link prediction despite not being trained on this task, highlighting the quality of the hierarchies discovered by our model.",

author = "Daniel Z{\"u}gner and Bertrand Charpentier and Sascha Geringer and Morgane Ayle and Stephan G{\"u}nnemann",

note = "Publisher Copyright: {\textcopyright} 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.; 10th International Conference on Learning Representations, ICLR 2022 ; Conference date: 25-04-2022 Through 29-04-2022",

year = "2022",

language = "English",

}

TY - CONF

T1 - END-TO-END LEARNING OF PROBABILISTIC HIERARCHIES ON GRAPHS

AU - Zügner, Daniel

AU - Charpentier, Bertrand

AU - Geringer, Sascha

AU - Ayle, Morgane

AU - Günnemann, Stephan

PY - 2022

Y1 - 2022

N2 - We propose a novel probabilistic model over hierarchies on graphs obtained by continuous relaxation of tree-based hierarchies. We draw connections to Markov chain theory, enabling us to perform hierarchical clustering by efficient end-to-end optimization of relaxed versions of quality metrics such as Dasgupta cost or Tree-Sampling Divergence (TSD). We show that our model learns rich, high-quality hierarchies present in 11 real world graphs, including a large graph with 2.3M nodes. Our model consistently outperforms recent as well as strong traditional baselines such as average linkage. Our model also obtains strong results on link prediction despite not being trained on this task, highlighting the quality of the hierarchies discovered by our model.

AB - We propose a novel probabilistic model over hierarchies on graphs obtained by continuous relaxation of tree-based hierarchies. We draw connections to Markov chain theory, enabling us to perform hierarchical clustering by efficient end-to-end optimization of relaxed versions of quality metrics such as Dasgupta cost or Tree-Sampling Divergence (TSD). We show that our model learns rich, high-quality hierarchies present in 11 real world graphs, including a large graph with 2.3M nodes. Our model consistently outperforms recent as well as strong traditional baselines such as average linkage. Our model also obtains strong results on link prediction despite not being trained on this task, highlighting the quality of the hierarchies discovered by our model.

UR - http://www.scopus.com/inward/record.url?scp=85150350517&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85150350517

T2 - 10th International Conference on Learning Representations, ICLR 2022

Y2 - 25 April 2022 through 29 April 2022

ER -

END-TO-END LEARNING OF PROBABILISTIC HIERARCHIES ON GRAPHS

Abstract

Conference

Other files and links

Fingerprint

Cite this